Logo Logo
Hilfe
Hilfe
Switch Language to English

Bengs, Viktor ORCID logoORCID: https://orcid.org/0000-0001-6988-6186; Haddenhorst, Björn und Hüllermeier, Eyke ORCID logoORCID: https://orcid.org/0000-0002-9944-4108 (Mai 2024): Identifying Copeland Winners in Dueling Bandits with Indifferences. 27th International Conference on Artificial Intelligence and Statistics (AISTATS 2024), Valencia, Spain, 2. - 4. May 2024. In: Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, Proceedings of Machine Learning Research Bd. 238 PMLR. S. 226-234 [PDF, 522kB]

Abstract

We consider the task of identifying the Copeland winner(s) in a dueling bandits problem with ternary feedback. This is an underexplored but practically relevant variant of the conventional dueling bandits problem, in which, in addition to strict preference between two arms, one may observe feedback in the form of an indifference. We provide a lower bound on the sample complexity for any learning algorithm finding the Copeland winner(s) with a fixed error probability. Moreover, we propose POCOWISTA, an algorithm with a sample complexity that almost matches this lower bound, and which shows excellent empirical performance, even for the conventional dueling bandits problem. For the case where the preference probabilities satisfy a specific type of stochastic transitivity, we provide a refined version with an improved worst case sample complexity.

Dokument bearbeiten Dokument bearbeiten